A polished cover with three incompatible scratch labels

OscarAbbott0010 · 5 Jul 2025, 23:49 UTC

Closed
OS
OscarAbbott0010
I borrowed the retained covers for our UR5e inspection proposal and found one sample in three folders. Good, scratched and doubtful. The bright line shifts when the light moves, but the folder names have become quite firm opinions. I want to get the actual sample decision and a repeatable view agreed before the team prices another camera. Or another light, which was the latest suggestion. Who should be in that first comparison?

20 replies

CH
ChenBell0616
Replying to OscarAbbott0010

The person who currently accepts the finish, with the actual covers and the existing appearance requirement, because you need to know what the station is meant to find before choosing equipment to find it.

11 points
OS
OscarAbbott0010
Replying to ChenBell0616

Finishing inspector has agreed to join. They say the doubtful folder was someone's temporary holding area, then a later export treated it as a defect class. That explains one opinion.

-1 points
DA
DavidArcher0432
Replying to OscarAbbott0010

Keep that export away from training data. Don't just rename the folder and assume nobody copied it. I'd tell the person building the dataset which labels are unverified.

16 points
VI
VictorBrooks0794
Replying to OscarAbbott0010

Who owns the labels once the inspector decides?

-3 points
OS
OscarAbbott0010
Replying to VictorBrooks0794

Our quality lead will own the sample decisions. Imaging can propose a review, but not overwrite the decision to improve a trial result.

2 points
JA
JaneBarnes0597
Replying to OscarAbbott0010

Has anyone checked the actual cover for a separate mark?

13 points
OS
OscarAbbott0010
Replying to JaneBarnes0597

Yes. The moving band isn't a scratch, but there's an edge scuff. Inspector hasn't finished deciding whether that scuff fails this product's requirement.

20 points
DA
DavidArcher0432
Replying to OscarAbbott0010

Then it stays doubtful. Explaining the big stripe doesn't grant the little scuff a pardon.

16 points
CH
ChenBell0616
Replying to OscarAbbott0010

I'd keep the scuff location with the images too, so the imaging person knows which physical feature the eventual decision concerns (not whichever line looks most dramatic).

16 points
JA
JaneBarnes0597
Replying to OscarAbbott0010

Could the same cover be presented repeatably for that comparison?

-2 points
OS
OscarAbbott0010
Replying to JaneBarnes0597

There's a static nest from the tooling trial. We need to check that the cover seats consistently in it; until now people have held the samples by hand.

13 points
VI
VictorBrooks0794
Replying to OscarAbbott0010

Show whoever loads it what seated looks like.

17 points
DA
DavidArcher0432
Replying to OscarAbbott0010

I'd still try a little deliberate presentation variation. A perfect nest photo won't tell you whether a minor normal seating difference makes the important scuff vanish.

0 points
CH
ChenBell0616
Replying to DavidArcher0432

Yes, once the nominal presentation is repeatable, have tooling and imaging define the variation to assess rather than letting everyone tilt it differently and call that the same trial.

10 points
OS
OscarAbbott0010
Replying to OscarAbbott0010

Quality has rejected the scuffed cover. We've retained it with the scuff marked on its record. Static captures are being compared at the agreed presentation and nearby positions.

15 points
DA
DavidArcher0432
Replying to OscarAbbott0010

Can you still see the scuff in those nearby positions? That's the result I'd care about, not whether the big reflection behaves nicely.

3 points
OS
OscarAbbott0010
Replying to DavidArcher0432

Not reliably in the initial set. The images are repeatable, but one presentation makes the scuff very faint. So we have a better reference and still no accepted imaging setup.

15 points
VI
VictorBrooks0794
Replying to OscarAbbott0010

Better to find that now.

11 points
CH
ChenBell0616
Replying to OscarAbbott0010

Keep that faint view in the supplier comparison, with the approved rejection reason; otherwise somebody may select only the convincing pictures when presenting their proposed lighting.

18 points
JA
JaneBarnes0597
Replying to OscarAbbott0010

Will the inspector review the next imaging trial too?

10 points

Discussion closed

This discussion is closed to new replies after six months without activity. Last activity: .